{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TDEKLBJQXY7374WR76XFJRCVAC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"df951dff6b7e22db54fa34a0b62063b9d19d05157b26ca11d1bf8bbffb355983","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T23:16:19Z","title_canon_sha256":"ffc62ba4115d536ec5f7caa6defd0dd76305127810c561a910ff597049b2db1c"},"schema_version":"1.0","source":{"id":"2501.12542","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12542","created_at":"2026-07-05T10:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12542v1","created_at":"2026-07-05T10:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12542","created_at":"2026-07-05T10:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"TDEKLBJQXY73","created_at":"2026-07-05T10:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"TDEKLBJQXY7374WR","created_at":"2026-07-05T10:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"TDEKLBJQ","created_at":"2026-07-05T10:03:54Z"}],"graph_snapshots":[{"event_id":"sha256:14ac0879ccbf6ae37555c81e19838c2429f7b31b9d7fa6adbc5630732555a434","target":"graph","created_at":"2026-07-05T10:03:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.12542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing approaches to enforcing design constraints in Reinforcement Learning (RL) applications often rely on training-time penalties in the reward function or training/inference-time invalid action masking, but these methods either cannot be modified after training, or are limited in the types of constraints that can be implemented. To address this limitation, we propose Reinforcement Learning Constrained Beam Search (RLCBS) for inference-time refinement in combinatorial optimization problems. This method respects flexible, inference-time constraints that support exclusion of invalid actions ","authors_text":"Chenhui Shao, Hanshen Yu, Jamal Yagoobi, Siyuan Chen","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T23:16:19Z","title":"Reinforcement Learning Constrained Beam Search for Parameter Optimization of Paper Drying Under Flexible Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12542","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:44ad398bc259bae75fbc3bce24e21914947cc95477fb4b946f8f73252c5aebb4","target":"record","created_at":"2026-07-05T10:03:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"df951dff6b7e22db54fa34a0b62063b9d19d05157b26ca11d1bf8bbffb355983","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T23:16:19Z","title_canon_sha256":"ffc62ba4115d536ec5f7caa6defd0dd76305127810c561a910ff597049b2db1c"},"schema_version":"1.0","source":{"id":"2501.12542","kind":"arxiv","version":1}},"canonical_sha256":"98c8a58530be3fbff2d1ffae54c45500b9abba64ca9a0d1e26abce4da195cdf4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98c8a58530be3fbff2d1ffae54c45500b9abba64ca9a0d1e26abce4da195cdf4","first_computed_at":"2026-07-05T10:03:54.695095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:54.695095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oHBtQYQp+bMne+OZUd2eWduMZQqBEweDPgMl5Y0rOtd+JEWSb50QsfzaUtAXyI/rPJyxceDlBiIxc8DB3jQQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:54.695610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12542","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44ad398bc259bae75fbc3bce24e21914947cc95477fb4b946f8f73252c5aebb4","sha256:14ac0879ccbf6ae37555c81e19838c2429f7b31b9d7fa6adbc5630732555a434"],"state_sha256":"2e684aea57c7d742e6fb76a1564d335e1c645927c2db6a0b6db71d4f16b9e1fc"}